INDEX

Explanations

code annotations

np_max-act · gemini-2.0-flash

The neuron detects code annotation tokens (e.g. annotation names and markers such as @VisibleForTesting, @Accessors, @RestrictTo, @TargetApi, @Specialization, @TruffleBoundary).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 flight

-0.07

 suffix

-0.06

 memcpy

-0.06

ись

-0.06

 metam

-0.06

того

-0.06

 Measurements

-0.06

 bladder

-0.06

)$

-0.06

Chance

-0.06

POSITIVE LOGITS

jer

0.07

.byId

0.06

都会

0.06

 hayvan

0.06

 fourth

0.06

_existing

0.06

<ActionResult

0.06

ой

0.06

 Serif

0.06

 choisir

0.06

Activations Density 0.006%

code annotations

The neuron detects code annotation tokens (e.g. annotation names and markers such as @VisibleForTesting, @Accessors, @RestrictTo, @TargetApi, @Specialization, @TruffleBoundary).

No Comments

No Known Activations

code annotations

The neuron detects code annotation tokens (e.g. annotation names and markers such as @VisibleForTesting, @Accessors, @RestrictTo, @TargetApi, @Specialization, @TruffleBoundary).

No Comments

No Known Activations